Panoramic Affordance Prediction

TL;DR

This paper introduces Panoramic Affordance Prediction, leveraging 360-degree imagery and a novel dataset to improve holistic scene understanding and affordance prediction in embodied AI, overcoming limitations of narrow FoV models.

Contribution

It presents the first panoramic affordance prediction framework and a large-scale benchmark dataset, PAP-12K, along with a coarse-to-fine pipeline inspired by human vision.

Findings

Existing methods fail on panoramic images due to distortion and limited FoV.

The proposed PAP framework significantly outperforms state-of-the-art baselines.

Panoramic perception enhances robustness in embodied AI applications.

Abstract

Affordance prediction serves as a critical bridge between perception and action in embodied AI. However, existing research is confined to pinhole camera models, which suffer from narrow Fields of View (FoV) and fragmented observations, often missing critical holistic environmental context. In this paper, we present the first exploration into Panoramic Affordance Prediction, utilizing 360-degree imagery to capture global spatial relationships and holistic scene understanding. To facilitate this novel task, we first introduce PAP-12K, a large-scale benchmark dataset containing over 1,000 ultra-high-resolution (12k, 11904 x 5952) panoramic images with over 12k carefully annotated QA pairs and affordance masks. Furthermore, we propose PAP, a training-free, coarse-to-fine pipeline inspired by the human foveal visual system to tackle the ultra-high resolution and severe distortion inherent in panoramic images. PAP employs recursive visual routing via grid prompting to progressively locate targets, applies an adaptive gaze mechanism to rectify local geometric distortions, and utilizes a cascaded grounding pipeline to extract precise instance-level masks. Experimental results on PAP-12K reveal that existing affordance prediction methods designed for standard perspective images suffer severe performance degradation and fail due to the unique challenges of panoramic vision. In contrast, PAP framework effectively overcomes these obstacles, significantly outperforming state-of-the-art baselines and highlighting the immense potential of panoramic perception for robust embodied intelligence.